US20070053575A1 - System and method for detecting a streak in a compressed gray scale image - Google Patents
System and method for detecting a streak in a compressed gray scale image Download PDFInfo
- Publication number
- US20070053575A1 US20070053575A1 US11/219,204 US21920405A US2007053575A1 US 20070053575 A1 US20070053575 A1 US 20070053575A1 US 21920405 A US21920405 A US 21920405A US 2007053575 A1 US2007053575 A1 US 2007053575A1
- Authority
- US
- United States
- Prior art keywords
- streak
- value
- peak
- compressed image
- cell blocks
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/60—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using transform coding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/52—Scale-space analysis, e.g. wavelet analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/98—Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns
- G06V10/993—Evaluation of the quality of the acquired pattern
Definitions
- the present invention relates generally to image processing, and more specifically relates to a system and method for detecting a streak in a gray scale image, such as an imaged check.
- the present invention addresses the above-mentioned problems, as well as others, by providing a system and method for detecting a streak in a gray scale document image.
- the invention provides a streak detection system for detecting a streak in a compressed image, comprising: an extraction system for extracting a DC value from each of a plurality of cell blocks in the compressed image; an identification system for identifying a peak DC value in each rank of cell blocks within the compressed image; and an analysis system for analyzing the peak DC values to determine if a streak exists in the compressed image.
- the invention provides a computer program product stored on a computer usable medium for detecting a streak in a compressed image, comprising: program code configured for extracting a DC value from each of a plurality of cell blocks in the compressed image; program code configured for identifying a peak DC value in each rank of cell blocks within the compressed image; and program code configured for analyzing the peak DC values to determine if a streak exists in the compressed image.
- the invention provides a method for detecting a streak in a compressed image, comprising: extracting a DC value from each of a plurality of cell blocks in the compressed image; identifying a peak DC value in each rank of cell blocks within the compressed image; and analyzing the peak DC values to determine if a streak exists in the compressed image.
- the invention provides deploying an application for detecting a streak in a compressed image, comprising: providing a computer infrastructure being operable to: extract a DC value from each of a plurality of cell blocks in the compressed image; identify a peak DC value in each rank of cell blocks within the compressed image; and analyze the peak DC values to determine if a streak exists in the compressed image.
- the invention provides computer software embodied in a propagated signal for detecting a streak in a compressed image, the computer software comprising instructions to cause a computer to perform the following functions: extract a DC value from each of a plurality of cell blocks in the compressed image; identify a peak DC value in each rank of cell blocks within the compressed image; and analyze the peak DC values to determine if a streak exists in the compressed image.
- FIG. 1 depicts a computer system having a streak detection system in accordance with the present invention.
- FIG. 2 depicts a document image being analyzed in accordance with the present invention.
- FIG. 3 depicts a check image having a streak.
- FIG. 4 depicts a plot of peak DCT[ 0 ] data gathered from the check image of FIG. 3 in accordance with the present invention.
- FIG. 5 depicts a check image without a streak.
- FIG. 6 depicts a plot of peak DCT[ 0 ] data gathered from the check image of FIG. 5 in accordance with the present invention.
- JPEG gray scale image 26 comprises a document image, and more specifically a check image, however it should be understood that the techniques described herein could be applied to any image.
- a whiteness value i.e., a DC coefficient
- streak detection system 18 comprises: an extraction system 20 for extracting a DCT[ 0 ] coefficient value from each cell block in the JPEG gray scale image 26 ; an identification system 22 for identifying the peak DCT[ 0 ] coefficient value in each “rank” (i.e., a row or column) of cell blocks aligned along the “direction of transport” of the imaged document; and an analysis system 24 for analyzing the identified set of peak DCT[ 0 ] coefficient values to determine if a streak exists.
- Systems 22 , 24 and 26 are described in further detail below with reference to FIGS. 2-6 .
- Streaks typically appear on checks (and other such documents) along the “direction of transport.” For instance, if a check is passed through a check processing device in a left-to-right horizontal manner, any streaking will typically appear horizontally across the check.
- An example of a JPEG check image 50 having a horizontal streak 52 is shown in FIG. 3 .
- image data is stored in a compressed format, such as JPEG.
- compression formats such as JPEG, encode an image into cell blocks, e.g., comprising 8 ⁇ 8 pixels.
- Each cell block includes one DC component, DCT[ 0 ], and 63 AC components DCT[1]-DCT[63].
- the 63 AC components comprise frequency information that allows the image to be compressed.
- the DC component contains a value that reflects an average “whiteness” of the cell block, i.e., the higher the DC value, the whiter or brighter the cell block.
- the present invention extracts and analyzes the DC components to determine whether a streak exists without having to totally decompress the image. Note that for the purposes of this disclosure the terms DC and DCT[ 0 ] are used interchangeably.
- FIG. 2 shows a document image 32 (e.g., a check) being analyzed in accordance with the present invention.
- the image 32 is vertically oriented only for the purposes of simplifying the explanation below.
- the direction of transport is along arrows 34 . Accordingly, any streaking on the image document 32 would be expected in the direction of arrows 34 .
- extraction system 20 first extracts a DCT[ 0 ] coefficient values from each cell block in the image 32 .
- the image comprises 30 ⁇ 15 cell blocks, with illustrative cell blocks 44 being shown in the leftmost vertical rank, in this case column, 36 . Extracting the DCT[ 0 ] coefficient value from each cell block of a JPEG image is a relatively simple process well understood in the art, requiring only a single decoding step.
- identification system 22 identifies the largest DCT[ 0 ] coefficient value in each cell block rank 42 , wherein a rank is a complete column or row of cell blocks oriented along the direction of transport.
- the largest DCT[ 0 ] coefficient value in each cell block rank 42 represents a “peak whiteness value” for the rank.
- cell block 38 represents the whitest cell block in the leftmost cell block rank 36 .
- Cell blocks 40 represent the whitest cell blocks in several of the other ranks 42 .
- FIGS. 3-6 provide an illustrative embodiment of an application of analysis system 24 .
- FIG. 3 depicts a check image 50 (320 pixels wide by 720 pixels tall) having a streak 52 .
- the highest DCT[ 0 ] coefficient value i.e., the whitest cell
- FIG. 4 the highest DCT[ 0 ] coefficient value
- These identified values form a set of peak DCT[ 0 ] coefficient values or peak whiteness levels.
- FIG. 4 shows a peak whiteness profile for each rank of cell blocks in the image 50 .
- the streak 52 in the check image 50 corresponds to a dip in the plot of the peak whiteness profile.
- an analysis of the plot indicates that there is a cluster of adjacent cell block ranks that have a peak whiteness level significantly less than rest of the check image, indicating a streak.
- FIG. 5 depicts a check image 60 that does not include a streak. As can be seen in the plot of FIG. 6 , there are no significant peaks or valleys, indicating no streak.
- Analysis system 24 which provides an automated process for identifying a streak from the set of peak DCT[ 0 ] coefficient values, could be implemented in any manner.
- the presence/absence of a streak in the check image 50 is established as follows:
- the computed SV is then compared to a threshold value to determine if the image is streaky. For instance, if the SV is above a predetermined threshold of 0.20 (or 20%), then the image is considered streaky. If the SV is below 20%, then the image is considered non-streaky.
- the normalized values were 35% and 9%, respectively.
- Experimental results for another image pair (not shown) were 42% and 6%, respectively.
- a threshold for the normalized values e.g. 20%, can be readily established to allow for easy discrimination between streaky and non-streaky images. Note that this methodology is illustrative in nature, and not meant to be limiting to scope of the invention. Based on actual check stock, corresponding images and the tolerance for streak acceptance, the above can be modified to ensure proper streak detection.
- Computer system 10 of FIG. 1 may comprise, e.g., a desktop, a laptop, a workstation, etc. Moreover, computer system 10 could be implemented as part of a client and/or a server.
- Computer system 10 generally includes a processor 12 , input/output (I/O) 14 , memory 16 , and bus 17 .
- the processor 12 may comprise a single processing unit, or be distributed across one or more processing units in one or more locations, e.g., on a client and server.
- Memory 16 may comprise any known type of data storage and/or transmission media, including magnetic media, optical media, random access memory (RAM), read-only memory (ROM), a data cache, a data object, etc.
- memory 16 may reside at a single physical location, comprising one or more types of data storage, or be distributed across a plurality of physical systems in various forms.
- I/O 14 may comprise any system for exchanging information to/from an external resource.
- External devices/resources may comprise any known type of external device, including a monitor/display, speakers, storage, another computer system, a hand-held device, keyboard, mouse, voice recognition system, speech output system, printer, facsimile, pager, etc.
- Bus 17 provides a communication link between each of the components in the computer system 10 and likewise may comprise any known type of transmission link, including electrical, optical, wireless, etc.
- additional components such as cache memory, communication systems, system software, etc., may be incorporated into computer system 10 .
- Access to computer system 10 may be provided over a network such as the Internet, a local area network (LAN), a wide area network (WAN), a virtual private network (VPN), etc. Communication could occur via a direct hardwired connection (e.g., serial port), or via an addressable connection that may utilize any combination of wireline and/or wireless transmission methods. Moreover, conventional network connectivity, such as Token Ring, Ethernet, WiFi or other conventional communications standards could be used. Still yet, connectivity could be provided by conventional TCP/IP sockets-based protocol. In this instance, an Internet service provider could be used to establish interconnectivity. Further, as indicated above, communication could occur in a client-server or server-server environment.
- LAN local area network
- WAN wide area network
- VPN virtual private network
- a computer system 10 comprising a streak detection system could be created, maintained and/or deployed by a service provider that offers the functions described herein for customers. That is, a service provider could offer to provide streak detection as described above.
- systems, functions, mechanisms, methods, engines and modules described herein can be implemented in hardware, software, or a combination of hardware and software. They may be implemented by any type of computer system or other apparatus adapted for carrying out the methods described herein.
- a typical combination of hardware and software could be a general-purpose computer system with a computer program that, when loaded and executed, controls the computer system such that it carries out the methods described herein.
- a specific use computer containing specialized hardware for carrying out one or more of the functional tasks of the invention could be utilized.
- part of all of the invention could be implemented in a distributed manner, e.g., over a network such as the Internet.
- the present invention can also be embedded in a computer program product, which comprises all the features enabling the implementation of the methods and functions described herein, and which—when loaded in a computer system—is able to carry out these methods and functions.
- Terms such as computer program, software program, program, program product, software, etc., in the present context mean any expression, in any language, code or notation, of a set of instructions intended to cause a system having an information processing capability to perform a particular function either directly or after either or both of the following: (a) conversion to another language, code or notation; and/or (b) reproduction in a different material form.
Abstract
A system and method for detecting a streak in a JPEG image. A system is provided that includes an extraction system for extracting a DC value from each cell block in the compressed image; an identification system for identifying a peak DC value in each rank of cell blocks within the compressed image; and an analysis system for analyzing the peak DC values to determine if a streak exists in the compressed image.
Description
- 1. Technical Field
- The present invention relates generally to image processing, and more specifically relates to a system and method for detecting a streak in a gray scale image, such as an imaged check.
- 2. Related Art
- With the passage of the Check 21 Act in 2004, the bank of first deposit is now allowed to send an electronic image, in lieu of an actual item (e.g., a paper check), for collection. In order to process an electronic image of a check, the image must be of sufficient quality. One of the quality attributes, as listed in ANSI 9.37, type 54 standard, is the absence of image streaks. Unfortunately, no automated techniques currently exist for effectively identifying streaks in such an image.
- Accordingly, a need exists for an automated system for detecting a streak in an electronic document image.
- The present invention addresses the above-mentioned problems, as well as others, by providing a system and method for detecting a streak in a gray scale document image.
- In a first aspect, the invention provides a streak detection system for detecting a streak in a compressed image, comprising: an extraction system for extracting a DC value from each of a plurality of cell blocks in the compressed image; an identification system for identifying a peak DC value in each rank of cell blocks within the compressed image; and an analysis system for analyzing the peak DC values to determine if a streak exists in the compressed image.
- In a second aspect, the invention provides a computer program product stored on a computer usable medium for detecting a streak in a compressed image, comprising: program code configured for extracting a DC value from each of a plurality of cell blocks in the compressed image; program code configured for identifying a peak DC value in each rank of cell blocks within the compressed image; and program code configured for analyzing the peak DC values to determine if a streak exists in the compressed image.
- In a third aspect, the invention provides a method for detecting a streak in a compressed image, comprising: extracting a DC value from each of a plurality of cell blocks in the compressed image; identifying a peak DC value in each rank of cell blocks within the compressed image; and analyzing the peak DC values to determine if a streak exists in the compressed image.
- In a fourth aspect, the invention provides deploying an application for detecting a streak in a compressed image, comprising: providing a computer infrastructure being operable to: extract a DC value from each of a plurality of cell blocks in the compressed image; identify a peak DC value in each rank of cell blocks within the compressed image; and analyze the peak DC values to determine if a streak exists in the compressed image.
- In a fifth aspect, the invention provides computer software embodied in a propagated signal for detecting a streak in a compressed image, the computer software comprising instructions to cause a computer to perform the following functions: extract a DC value from each of a plurality of cell blocks in the compressed image; identify a peak DC value in each rank of cell blocks within the compressed image; and analyze the peak DC values to determine if a streak exists in the compressed image.
- These and other features of this invention will be more readily understood from the following detailed description of the various aspects of the invention taken in conjunction with the accompanying drawings in which:
-
FIG. 1 depicts a computer system having a streak detection system in accordance with the present invention. -
FIG. 2 depicts a document image being analyzed in accordance with the present invention. -
FIG. 3 depicts a check image having a streak. -
FIG. 4 depicts a plot of peak DCT[0] data gathered from the check image ofFIG. 3 in accordance with the present invention. -
FIG. 5 depicts a check image without a streak. -
FIG. 6 depicts a plot of peak DCT[0] data gathered from the check image ofFIG. 5 in accordance with the present invention. - Referring now to the drawings, a
computer system 10 is shown having astreak detection system 18 for determining if a JPEGgray scale image 26 includes astreak 28, and outputting astreak detection result 30, e.g., a yes, a no, a value, etc. In the examples described herein, JPEGgray scale image 26 comprises a document image, and more specifically a check image, however it should be understood that the techniques described herein could be applied to any image. Moreover, while the illustrative embodiments describe a system for analyzing JPEG gray scale images, the techniques described herein could be applied to any image format in which a whiteness value (i.e., a DC coefficient) can be readily extracted from a pixel cell block. - In this illustrative embodiment,
streak detection system 18 comprises: anextraction system 20 for extracting a DCT[0] coefficient value from each cell block in the JPEGgray scale image 26; anidentification system 22 for identifying the peak DCT[0] coefficient value in each “rank” (i.e., a row or column) of cell blocks aligned along the “direction of transport” of the imaged document; and ananalysis system 24 for analyzing the identified set of peak DCT[0] coefficient values to determine if a streak exists.Systems FIGS. 2-6 . - Streaks typically appear on checks (and other such documents) along the “direction of transport.” For instance, if a check is passed through a check processing device in a left-to-right horizontal manner, any streaking will typically appear horizontally across the check. An example of a
JPEG check image 50 having ahorizontal streak 52 is shown inFIG. 3 . - In most instances, image data is stored in a compressed format, such as JPEG. As is known in the art, compression formats, such as JPEG, encode an image into cell blocks, e.g., comprising 8×8 pixels. Each cell block includes one DC component, DCT[0], and 63 AC components DCT[1]-DCT[63]. The 63 AC components comprise frequency information that allows the image to be compressed. The DC component contains a value that reflects an average “whiteness” of the cell block, i.e., the higher the DC value, the whiter or brighter the cell block. The present invention extracts and analyzes the DC components to determine whether a streak exists without having to totally decompress the image. Note that for the purposes of this disclosure the terms DC and DCT[0] are used interchangeably.
-
FIG. 2 shows a document image 32 (e.g., a check) being analyzed in accordance with the present invention. (Note that theimage 32 is vertically oriented only for the purposes of simplifying the explanation below.) In this example, the direction of transport is alongarrows 34. Accordingly, any streaking on theimage document 32 would be expected in the direction ofarrows 34. To determine if any streaking exists,extraction system 20 first extracts a DCT[0] coefficient values from each cell block in theimage 32. In this example, the image comprises 30×15 cell blocks, withillustrative cell blocks 44 being shown in the leftmost vertical rank, in this case column, 36. Extracting the DCT[0] coefficient value from each cell block of a JPEG image is a relatively simple process well understood in the art, requiring only a single decoding step. - Once the DCT[0] coefficient values are extracted,
identification system 22 then identifies the largest DCT[0] coefficient value in eachcell block rank 42, wherein a rank is a complete column or row of cell blocks oriented along the direction of transport. The largest DCT[0] coefficient value in eachcell block rank 42 represents a “peak whiteness value” for the rank. For instance, in the illustration shown inFIG. 2 ,cell block 38 represents the whitest cell block in the leftmostcell block rank 36.Cell blocks 40 represent the whitest cell blocks in several of theother ranks 42. Once the whitest cell block in eachrank 42 is identified, the DC values associated with those cell blocks can be analyzed byanalysis system 24 to determine if a streak exists. -
FIGS. 3-6 provide an illustrative embodiment of an application ofanalysis system 24. As can be seen,FIG. 3 depicts a check image 50 (320 pixels wide by 720 pixels tall) having astreak 52. In the orientation shown, there are 40×90 JPEG cell blocks, 40 in the horizontal direction and 90 in the vertical direction (in this case, the direction of transport). For each rank of cell blocks oriented along the direction of transport, the highest DCT[0] coefficient value (i.e., the whitest cell) is identified and plotted, as shown inFIG. 4 . These identified values form a set of peak DCT[0] coefficient values or peak whiteness levels. Thus, the plot ofFIG. 4 shows a peak whiteness profile for each rank of cell blocks in theimage 50. Note that thestreak 52 in thecheck image 50 corresponds to a dip in the plot of the peak whiteness profile. Thus, an analysis of the plot indicates that there is a cluster of adjacent cell block ranks that have a peak whiteness level significantly less than rest of the check image, indicating a streak. -
FIG. 5 depicts a check image 60 that does not include a streak. As can be seen in the plot ofFIG. 6 , there are no significant peaks or valleys, indicating no streak. -
Analysis system 24, which provides an automated process for identifying a streak from the set of peak DCT[0] coefficient values, could be implemented in any manner. In one illustrative embodiment, the presence/absence of a streak in thecheck image 50 is established as follows: - (1) For each of the 40 cell block ranks from which a peak DCT[0] coefficient value was obtained, discard the first and last four values to eliminate any edge effects contained in the image, e.g., black borders along the check image.
- (2) Of the remaining 32 values, place them in the descending order of peak DCT[0] coefficient value.
- (3)Ignore the highest four values, and take the average of the next four. Label this as the average video.
- (4) A streak value (SV) is computed by taking the difference between the average video (AV) and the lowest DCT[0] coefficient value (LV), normalized with respect to the average video, i.e., SV=(AV−LV)/AV.
- (5) The computed SV is then compared to a threshold value to determine if the image is streaky. For instance, if the SV is above a predetermined threshold of 0.20 (or 20%), then the image is considered streaky. If the SV is below 20%, then the image is considered non-streaky.
- For the streaky and non-streak images shown images in
FIGS. 3 and 5 , the normalized values were 35% and 9%, respectively. Experimental results for another image pair (not shown) were 42% and 6%, respectively. Thus, a threshold for the normalized values, e.g., 20%, can be readily established to allow for easy discrimination between streaky and non-streaky images. Note that this methodology is illustrative in nature, and not meant to be limiting to scope of the invention. Based on actual check stock, corresponding images and the tolerance for streak acceptance, the above can be modified to ensure proper streak detection. - Note that
computer system 10 ofFIG. 1 may comprise, e.g., a desktop, a laptop, a workstation, etc. Moreover,computer system 10 could be implemented as part of a client and/or a server.Computer system 10 generally includes aprocessor 12, input/output (I/O) 14,memory 16, andbus 17. Theprocessor 12 may comprise a single processing unit, or be distributed across one or more processing units in one or more locations, e.g., on a client and server.Memory 16 may comprise any known type of data storage and/or transmission media, including magnetic media, optical media, random access memory (RAM), read-only memory (ROM), a data cache, a data object, etc. Moreover,memory 16 may reside at a single physical location, comprising one or more types of data storage, or be distributed across a plurality of physical systems in various forms. - I/
O 14 may comprise any system for exchanging information to/from an external resource. External devices/resources may comprise any known type of external device, including a monitor/display, speakers, storage, another computer system, a hand-held device, keyboard, mouse, voice recognition system, speech output system, printer, facsimile, pager, etc.Bus 17 provides a communication link between each of the components in thecomputer system 10 and likewise may comprise any known type of transmission link, including electrical, optical, wireless, etc. Although not shown, additional components, such as cache memory, communication systems, system software, etc., may be incorporated intocomputer system 10. - Access to
computer system 10 may be provided over a network such as the Internet, a local area network (LAN), a wide area network (WAN), a virtual private network (VPN), etc. Communication could occur via a direct hardwired connection (e.g., serial port), or via an addressable connection that may utilize any combination of wireline and/or wireless transmission methods. Moreover, conventional network connectivity, such as Token Ring, Ethernet, WiFi or other conventional communications standards could be used. Still yet, connectivity could be provided by conventional TCP/IP sockets-based protocol. In this instance, an Internet service provider could be used to establish interconnectivity. Further, as indicated above, communication could occur in a client-server or server-server environment. - It should be appreciated that the teachings of the present invention could be offered as a business method on a subscription or fee basis. For example, a
computer system 10 comprising a streak detection system could be created, maintained and/or deployed by a service provider that offers the functions described herein for customers. That is, a service provider could offer to provide streak detection as described above. - It is understood that the systems, functions, mechanisms, methods, engines and modules described herein can be implemented in hardware, software, or a combination of hardware and software. They may be implemented by any type of computer system or other apparatus adapted for carrying out the methods described herein. A typical combination of hardware and software could be a general-purpose computer system with a computer program that, when loaded and executed, controls the computer system such that it carries out the methods described herein. Alternatively, a specific use computer, containing specialized hardware for carrying out one or more of the functional tasks of the invention could be utilized. In a further embodiment, part of all of the invention could be implemented in a distributed manner, e.g., over a network such as the Internet.
- The present invention can also be embedded in a computer program product, which comprises all the features enabling the implementation of the methods and functions described herein, and which—when loaded in a computer system—is able to carry out these methods and functions. Terms such as computer program, software program, program, program product, software, etc., in the present context mean any expression, in any language, code or notation, of a set of instructions intended to cause a system having an information processing capability to perform a particular function either directly or after either or both of the following: (a) conversion to another language, code or notation; and/or (b) reproduction in a different material form.
- The foregoing description of the invention has been presented for purposes of illustration and description. It is not intended to be exhaustive or to limit the invention to the precise form disclosed, and obviously, many modifications and variations are possible. Such modifications and variations that may be apparent to a person skilled in the art are intended to be included within the scope of this invention as defined by the accompanying claims.
Claims (22)
1. A streak detection system for detecting a streak in a compressed image, comprising:
an extraction system for extracting a DC value from each of a plurality of cell blocks in the compressed image;
an identification system for identifying a peak DC value in each rank of cell blocks within the compressed image; and
an analysis system for analyzing the peak DC values to determine if a streak exists in the compressed image.
2. The streak detection system of claim 1 , wherein the compressed image comprises a JPEG image.
3. The streak detection system of claim 1 , wherein the compressed image comprises an image of a check.
4. The streak detection system of claim 3 , wherein each rank of cell blocks is oriented along a direction of travel of the check.
5. The streak detection system of claim 1 , wherein each rank of cell blocks comprises a row or column of cell blocks.
6. The streak detection system of claim 1 , wherein the analysis system calculates a streak value and compares the streak value to a threshold value to determine if a streak exists.
7. The streak detection system of claim 6 , wherein the streak value is computed according to the following:
for each rank of the cell blocks from which a peak DC coefficient value was obtained, discard the first n and last m values to eliminate any edge effects, wherein n and m are predetermined integers;
of the remaining peak DC coefficient values, place them in a descending order;
ignore the highest four peak DC coefficient values, and compute an average of the next four highest peak DC coefficient values;
compute the streak value as a difference between the computed average and a lowest peak DC coefficient value, normalized with respect to the computed average.
8. A computer program product stored on a computer usable medium for detecting a streak in a compressed image, comprising:
program code configured for extracting a DC value from each of a plurality of cell blocks in the compressed image;
program code configured for identifying a peak DC value in each rank of cell blocks within the compressed image; and
program code configured for analyzing the peak DC values to determine if a streak exists in the compressed image.
9. The computer program product of claim 8 , wherein the compressed image comprises a JPEG image.
10. The computer program product of claim 8 , wherein the compressed image comprises an image of a check.
11. The computer program product of claim 10 , wherein each rank of cell blocks is oriented along a direction of travel of the check.
12. The computer program product of claim 8 , wherein each rank of cell blocks comprises a row or column of cell blocks.
13. The computer program product of claim 8 , wherein the program code configured for analyzing the peak DC values calculates a streak value and compares the streak value to a threshold value to determine if a streak exists.
14. The computer program product of claim 13 , wherein the streak value is computed according to the following:
for each rank of the cell blocks from which a peak DC coefficient value was obtained, discard the first n and last m values to eliminate any edge effects, wherein n and m are predetermined integers;
of the remaining peak DC coefficient values, place them in a descending order;
ignore the highest four peak DC coefficient values, and compute an average of the next four highest peak DC coefficient values;
compute the streak value as a difference between the computed average and a lowest peak DC coefficient value, normalized with respect to the computed average.
15. A method for detecting a streak in a compressed image, comprising:
extracting a DC value from each of a plurality of cell blocks in the compressed image;
identifying a peak DC value in each rank of cell blocks within the compressed image; and
analyzing the peak DC values to determine if a streak exists in the compressed image.
16. The method of claim 15 , wherein the compressed image comprises a JPEG image.
17. The method of claim 15 , wherein the compressed image comprises an image of a check.
18. The method of claim 17 , wherein each rank of cell blocks is oriented along a direction of travel of the check.
19. The method of claim 15 , wherein each rank of cell blocks comprises a row or column of cell blocks.
20. The method of claim 15 , wherein the step of analyzing the peak DC values calculates a streak value and compares the streak value to a threshold value to determine if a streak exists.
21. The method of claim 20 , wherein the streak value is computed according to the following steps:
for each rank of the cell blocks from which a peak DC coefficient value was obtained, discard the first n and last m values to eliminate any edge effects, wherein n and m are predetermined integers;
of the remaining peak DC coefficient values, place them in a descending order;
ignore the highest four peak DC coefficient values, and compute an average of the next four highest peak DC coefficient values;
compute the streak value as a difference between the computed average and a lowest peak DC coefficient value, normalized with respect to the computed average.
22. A method for deploying an application for detecting a streak in a compressed image, comprising:
providing a computer infrastructure being operable to:
extract a DC value from each of a plurality of cell blocks in the compressed image;
identify a peak DC value in each rank of cell blocks within the compressed image; and
analyze the peak DC values to determine if a streak exists in the compressed image.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US11/219,204 US7522761B2 (en) | 2005-09-02 | 2005-09-02 | System and method for detecting a streak in a compressed gray scale image |
US12/366,704 US7885474B2 (en) | 2005-09-02 | 2009-02-06 | Solution for detecting a streak in a compressed gray scale image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US11/219,204 US7522761B2 (en) | 2005-09-02 | 2005-09-02 | System and method for detecting a streak in a compressed gray scale image |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/366,704 Continuation US7885474B2 (en) | 2005-09-02 | 2009-02-06 | Solution for detecting a streak in a compressed gray scale image |
Publications (2)
Publication Number | Publication Date |
---|---|
US20070053575A1 true US20070053575A1 (en) | 2007-03-08 |
US7522761B2 US7522761B2 (en) | 2009-04-21 |
Family
ID=37830083
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US11/219,204 Expired - Fee Related US7522761B2 (en) | 2005-09-02 | 2005-09-02 | System and method for detecting a streak in a compressed gray scale image |
US12/366,704 Expired - Fee Related US7885474B2 (en) | 2005-09-02 | 2009-02-06 | Solution for detecting a streak in a compressed gray scale image |
Family Applications After (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/366,704 Expired - Fee Related US7885474B2 (en) | 2005-09-02 | 2009-02-06 | Solution for detecting a streak in a compressed gray scale image |
Country Status (1)
Country | Link |
---|---|
US (2) | US7522761B2 (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090208140A1 (en) * | 2006-05-01 | 2009-08-20 | Georgia Tech Research Corporation | Automatic Video Quality Measurement System and Method Based on Spatial-Temporal Coherence Metrics |
US20090232203A1 (en) * | 2006-05-01 | 2009-09-17 | Nuggehally Sampath Jayant | Expert System and Method for Elastic Encoding of Video According to Regions of Interest |
US20100118956A1 (en) * | 2008-11-12 | 2010-05-13 | Sony Corporation | Method and device for extracting a mean luminance variance from a sequence of video frames |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7522761B2 (en) * | 2005-09-02 | 2009-04-21 | International Business Machines Corporation | System and method for detecting a streak in a compressed gray scale image |
US8401280B2 (en) * | 2009-12-21 | 2013-03-19 | Electronics And Telecommunications Research Institute | Device for improving stereo matching results, method of improving stereo matching results using the device, and system for receiving stereo matching results |
US8930362B2 (en) | 2011-03-31 | 2015-01-06 | Infosys Limited | System and method for streak discovery and prediction |
Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4491963A (en) * | 1982-08-17 | 1985-01-01 | Pitney Bowes Inc. | Correction of imaging imperfections |
US5917957A (en) * | 1996-04-08 | 1999-06-29 | Advantest Corporation | Method of and apparatus for processing an image |
US6023334A (en) * | 1993-10-27 | 2000-02-08 | Toshiba Engineering Corporation | Method and apparatus for detecting minute irregularities on the surface of an object |
US6335982B1 (en) * | 1996-06-26 | 2002-01-01 | Toshiba Engineering Corporation | Method and apparatus for inspecting streak |
US6393161B1 (en) * | 1999-04-26 | 2002-05-21 | Xerox Corporation | Software system for minimizing image defects in a hard-copy input scanner |
US6628842B1 (en) * | 1999-06-22 | 2003-09-30 | Fuji Photo Film Co., Ltd. | Image processing method and apparatus |
US6667815B1 (en) * | 1998-09-30 | 2003-12-23 | Fuji Photo Film Co., Ltd. | Method and apparatus for processing images |
US6717622B2 (en) * | 2001-03-30 | 2004-04-06 | Koninklijke Philips Electronics N.V. | System and method for scalable resolution enhancement of a video image |
US20040136603A1 (en) * | 2002-07-18 | 2004-07-15 | Vitsnudel Iiia | Enhanced wide dynamic range in imaging |
US6823089B1 (en) * | 2000-09-28 | 2004-11-23 | Eastman Kodak Company | Method of determining the extent of blocking and contouring artifacts in a digital image |
US7058236B2 (en) * | 2001-05-25 | 2006-06-06 | Canon Kabushiki Kaisha | Image reading apparatus and program |
US20060182331A1 (en) * | 2005-02-17 | 2006-08-17 | Gilson Jonathan C | System and method for embedding check data in a check image |
US7167580B2 (en) * | 2003-04-30 | 2007-01-23 | Unisys Corporation | Image quality assurance systems and methodologies for improving the identification of and access speed to image quality suspects in documents |
US7289679B2 (en) * | 2003-08-12 | 2007-10-30 | International Business Machines Corporation | System and method for measuring image quality using compressed image data |
US7388989B2 (en) * | 2004-11-19 | 2008-06-17 | Xerox Corporation | Method for run-time streak detection by profile analysis |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5692065A (en) * | 1994-08-18 | 1997-11-25 | International Business Machines Corporation | Apparatus and method for determining image quality |
JPH11225346A (en) | 1998-02-05 | 1999-08-17 | Hitachi Ltd | Method and system for checking display monitor image |
JP3989112B2 (en) | 1999-01-12 | 2007-10-10 | 株式会社東芝 | White scratch signal level suppression device for solid-state imaging device |
JP2002262083A (en) | 2001-03-06 | 2002-09-13 | Ricoh Co Ltd | Image processor |
US7522761B2 (en) * | 2005-09-02 | 2009-04-21 | International Business Machines Corporation | System and method for detecting a streak in a compressed gray scale image |
-
2005
- 2005-09-02 US US11/219,204 patent/US7522761B2/en not_active Expired - Fee Related
-
2009
- 2009-02-06 US US12/366,704 patent/US7885474B2/en not_active Expired - Fee Related
Patent Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4491963A (en) * | 1982-08-17 | 1985-01-01 | Pitney Bowes Inc. | Correction of imaging imperfections |
US6023334A (en) * | 1993-10-27 | 2000-02-08 | Toshiba Engineering Corporation | Method and apparatus for detecting minute irregularities on the surface of an object |
US5917957A (en) * | 1996-04-08 | 1999-06-29 | Advantest Corporation | Method of and apparatus for processing an image |
US6335982B1 (en) * | 1996-06-26 | 2002-01-01 | Toshiba Engineering Corporation | Method and apparatus for inspecting streak |
US6667815B1 (en) * | 1998-09-30 | 2003-12-23 | Fuji Photo Film Co., Ltd. | Method and apparatus for processing images |
US6393161B1 (en) * | 1999-04-26 | 2002-05-21 | Xerox Corporation | Software system for minimizing image defects in a hard-copy input scanner |
US6628842B1 (en) * | 1999-06-22 | 2003-09-30 | Fuji Photo Film Co., Ltd. | Image processing method and apparatus |
US6823089B1 (en) * | 2000-09-28 | 2004-11-23 | Eastman Kodak Company | Method of determining the extent of blocking and contouring artifacts in a digital image |
US6717622B2 (en) * | 2001-03-30 | 2004-04-06 | Koninklijke Philips Electronics N.V. | System and method for scalable resolution enhancement of a video image |
US7058236B2 (en) * | 2001-05-25 | 2006-06-06 | Canon Kabushiki Kaisha | Image reading apparatus and program |
US20040136603A1 (en) * | 2002-07-18 | 2004-07-15 | Vitsnudel Iiia | Enhanced wide dynamic range in imaging |
US7167580B2 (en) * | 2003-04-30 | 2007-01-23 | Unisys Corporation | Image quality assurance systems and methodologies for improving the identification of and access speed to image quality suspects in documents |
US7289679B2 (en) * | 2003-08-12 | 2007-10-30 | International Business Machines Corporation | System and method for measuring image quality using compressed image data |
US7388989B2 (en) * | 2004-11-19 | 2008-06-17 | Xerox Corporation | Method for run-time streak detection by profile analysis |
US20060182331A1 (en) * | 2005-02-17 | 2006-08-17 | Gilson Jonathan C | System and method for embedding check data in a check image |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090208140A1 (en) * | 2006-05-01 | 2009-08-20 | Georgia Tech Research Corporation | Automatic Video Quality Measurement System and Method Based on Spatial-Temporal Coherence Metrics |
US20090232203A1 (en) * | 2006-05-01 | 2009-09-17 | Nuggehally Sampath Jayant | Expert System and Method for Elastic Encoding of Video According to Regions of Interest |
US8331436B2 (en) | 2006-05-01 | 2012-12-11 | Georgia Tech Research Corporation | Expert system and method for elastic encoding of video according to regions of interest |
US8488915B2 (en) * | 2006-05-01 | 2013-07-16 | Georgia Tech Research Corporation | Automatic video quality measurement system and method based on spatial-temporal coherence metrics |
US20100118956A1 (en) * | 2008-11-12 | 2010-05-13 | Sony Corporation | Method and device for extracting a mean luminance variance from a sequence of video frames |
Also Published As
Publication number | Publication date |
---|---|
US20100195895A1 (en) | 2010-08-05 |
US7885474B2 (en) | 2011-02-08 |
US7522761B2 (en) | 2009-04-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8837830B2 (en) | Finding text in natural scenes | |
US8825682B2 (en) | Architecture for mixed media reality retrieval of locations and registration of images | |
US10152648B2 (en) | Method and apparatus for determining a document type of a digital document | |
US8868555B2 (en) | Computation of a recongnizability score (quality predictor) for image retrieval | |
US8510283B2 (en) | Automatic adaption of an image recognition system to image capture devices | |
US8856108B2 (en) | Combining results of image retrieval processes | |
US7885474B2 (en) | Solution for detecting a streak in a compressed gray scale image | |
US8503797B2 (en) | Automatic document classification using lexical and physical features | |
US8391599B1 (en) | Systems and methods for adaptive binarization of an image | |
US20170287252A1 (en) | Counterfeit Document Detection System and Method | |
US20090100050A1 (en) | Client device for interacting with a mixed media reality recognition system | |
US20020067857A1 (en) | System and method for classification of images and videos | |
US10198628B2 (en) | Method and apparatus for determining a document suitability for server-based optical character recognition (OCR) processing | |
CN111144366A (en) | Strange face clustering method based on joint face quality assessment | |
CN112270309A (en) | Vehicle access point equipment snapshot quality evaluation method and device and readable medium | |
CN110895811B (en) | Image tampering detection method and device | |
CN115240203A (en) | Service data processing method, device, equipment and storage medium | |
CN106611148B (en) | Image-based offline formula identification method and device | |
CN114399497A (en) | Text image quality detection method and device, computer equipment and storage medium | |
US7239748B2 (en) | System and method for segmenting an electronic image | |
Chen et al. | Alpha-trimmed image estimation for JPEG steganography detection | |
JP5283267B2 (en) | Content identification method and apparatus | |
CN112016348A (en) | Face authenticity identification method and device | |
CN111881778B (en) | Method, apparatus, device and computer readable medium for text detection | |
Rodriguez et al. | Multi-class classification fusion using boosting for identifying steganography methods |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: INTERNATIONAL BUSINESS MACHINES CORPORATION, NEW Y Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:PRAKASH, RAVINDER;SATHE, MADHURA;REEL/FRAME:016841/0287 Effective date: 20050831 |
|
FEPP | Fee payment procedure |
Free format text: PAYOR NUMBER ASSIGNED (ORIGINAL EVENT CODE: ASPN); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY |
|
REMI | Maintenance fee reminder mailed | ||
FPAY | Fee payment |
Year of fee payment: 4 |
|
SULP | Surcharge for late payment | ||
REMI | Maintenance fee reminder mailed | ||
LAPS | Lapse for failure to pay maintenance fees | ||
STCH | Information on status: patent discontinuation |
Free format text: PATENT EXPIRED DUE TO NONPAYMENT OF MAINTENANCE FEES UNDER 37 CFR 1.362 |
|
FP | Lapsed due to failure to pay maintenance fee |
Effective date: 20170421 |